Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1037 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.4689. Min Act: -0.1700

Data Index: 6284 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.4689. Min Act: -0.1700

Data Index: 630073 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.4689. Min Act: -0.1700

Data Index: 1303263 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.4064. Min Act: -0.1700

Data Index: 54687 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3751. Min Act: -0.1700

Data Index: 221988 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3751. Min Act: -0.1700

Data Index: 629883 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3751. Min Act: -0.1700

Data Index: 281957 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3439. Min Act: -0.1700

Data Index: 503096 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3439. Min Act: -0.1700

Data Index: 568721 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3751. Min Act: -0.1700

Data Index: 1109365 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3126. Min Act: -0.1700

Data Index: 594880 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2501. Min Act: -0.1700

Data Index: 962347 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.3126. Min Act: -0.1700

Data Index: 1216598 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2814. Min Act: -0.1700

Data Index: 1094842 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2501. Min Act: -0.1700

Data Index: 215390 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2189. Min Act: -0.1700

Data Index: 754828 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2501. Min Act: -0.1700

Data Index: 816647 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2501. Min Act: -0.1700

Data Index: 764359 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2189. Min Act: -0.1700

Data Index: 1196431 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.2189. Min Act: -0.1700

Data Index: 372813 (C4 (Web Text))

Max Activating Token Index: 942